io.github.aidemd-mcp/server

Est-ce que io.github.aidemd-mcp/server est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.aidemd-mcp/server » est classé « Vérifié ». Aucun comportement malveillant détecté au test comportemental. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Versions auditées & empreintes

Vérifiez la version que vous utilisez : son empreinte doit correspondre à celle listée ici — sinon vous n'utilisez pas la version auditée.

⚠ La dernière version publiée (0.11.1) n'a pas encore été auditée. Un nouveau pentest est programmé ; les verdicts ci-dessous portent sur les versions listées.

Vous utilisez ce serveur ? Suivez-le (créez un compte) pour être alerté dès qu'une nouvelle version paraît ou que le verdict change.

Les 10 outils

• aide_discover≈ 320 tokens

  Scan for .aide spec files in this project. Returns a tree map of where specs live, following progressive disclosure. Without a path: returns a lightweight project-wide map — file locations and types only, no content. Use this once to understand the project's spec architecture. With a path: the response opens with the ancestor chain — the cascading intent lineage from project root down to the target directory, with each ancestor showing its description and alignment status (aligned/misaligned when set). The ancestor chain gives you the full inherited context before you read a single spec body. After the ancestor chain comes the detailed subtree of the target directory — summaries extracted from file content and anomaly warnings. Use this to drill into the area you're working on. .aide fi

  Paramètres, retour & exemple (1)

  Paramètres

  • path · string · optionnel
    Subdirectory to drill into. When provided, the response opens with the ancestor chain — the cascading intent lineage from root to target, each ancestor showing its description and alignment status — followed by the detailed subtree with summaries and warnings. When omitted, returns a shallow project-wide map (locations and types only).

  Exemple d'appel

  {"name": "aide_discover", "arguments": {"path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_read≈ 120 tokens

  Read an .aide spec file with full context. Returns the file content, its classified type (intent/research/plan/todo), related specs in the same directory, and links found in the content (relative paths, inline references, URLs). Use this after aide_discover to drill into a specific spec.

  Paramètres, retour & exemple (1)

  Paramètres

  • path · string · requis
    Path to the .aide file to read

  Exemple d'appel

  {"name": "aide_read", "arguments": {"path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_scaffold≈ 238 tokens

  Create new .aide spec files with automatic naming convention enforcement. Handles the naming rules: intent specs are .aide by default, but become intent.aide when research.aide exists in the same folder. Creating a research.aide auto-renames any existing .aide to intent.aide. Types: - intent — Strategy, contracts, anti-patterns - research — Sources, data, patterns (triggers rename of existing .aide) - both — Creates research.aide + intent.aide pair - todo — QA re-alignment document for QA agents - plan -- Architect's implementation plan (no naming interaction with intent/research)

  Paramètres, retour & exemple (2)

  Paramètres

  • type · string · requis · intent | research | both | todo | plan
    Type of .aide file to create
  • directory · string · requis
    Directory where the .aide file(s) will be created

  Exemple d'appel

  {"name": "aide_scaffold", "arguments": {"type": "intent", "directory": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_cleanup≈ 348 tokens

  Remove a module's pipeline ephemerals (plan.aide, todo.aide, brief.aide) once that module's cycle has closed, leaving the code and the intent specs as the durable record. It never removes, rewrites or reads anything else: intent specs, research specs, code, and .aide/session.aide are all out of reach. Where plan.aide exists, it refuses unless every plan checkbox is checked and any todo.aide present is fully checked; a missing todo.aide does not block. Where there is no plan.aide, it removes a todo.aide that is fully checked, and refuses a brief.aide (which is removed only together with its plan), a todo.aide with no checkboxes, or a folder with no ephemerals at all. A refusal lists each unchecked item with its file and line, and nothing is removed. By default a plan.aide with no checkboxe

  Paramètres, retour & exemple (3)

  Paramètres

  • path · string · requis
    The module directory whose ephemerals to remove, relative to the project root
  • dryRun · boolean · optionnel
    Optional. Removes nothing and only reports what a real call would remove. Agents closing a module omit it.
  • allowEmptyPlan · boolean · optionnel
    Optional, off by default. Lets a plan.aide with no checkboxes pass. Overrides nothing else, and has no effect where there is no plan.aide.

  Exemple d'appel

  {"name": "aide_cleanup", "arguments": {"path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_validate≈ 142 tokens

  Health check for .aide spec files in the project. Detects orphaned specs (in folders with no orchestrator), missing specs (orchestrators with 3+ helper imports but no .aide), naming conflicts (.aide + intent.aide in same folder), broken links, orphaned research (research.aide without intent spec), and missing descriptions (specs with no description field in frontmatter).

  Paramètres, retour & exemple (1)

  Paramètres

  • path · string · optionnel
    Subdirectory to validate (defaults to entire project)

  Exemple d'appel

  {"name": "aide_validate", "arguments": {"path": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_upgrade≈ 656 tokens

  Compare the AIDE methodology artifacts in this project against the canonical versions and return structured JSON results grouped by category. Use this when the user asks to update AIDE, sync AIDE, refresh AIDE, check for AIDE updates, or bring AIDE up to date. This is NOT for editing user .aide specs — it inspects methodology infrastructure only. The tool uses a two-call pattern for progressive disclosure: **First call (no `category` param):** Returns a lightweight summary — every category with file names, statuses, and counts, but NO file content. Use this to understand what has drifted and present a summary to the user. Ask which categories they want to apply. **Second call (with `category` param):** The tool writes all differs/missing files directly to disk itself and returns a manif

  Paramètres, retour & exemple (5)

  Paramètres

  • path · string · optionnel
    Custom project root path (defaults to server working directory)
  • category · string · optionnel · pointer-stub | methodology-docs | version-metadata | commands | agents | skills | mcp | ide
    When provided, applies that category. For package-owned categories the call writes all differs/missing files to disk and returns a manifest (no canonicalContent). For `brain` it inserts missing sections (no `brainChange`), previews one change (`brainChange` alone), or applies it (`brainChange` + `beforeHash`); it never rewrites an existing section outside an applied change. When omitted, return all categories as metadata-only summaries (no canonicalContent fields).
  • framework · string · optionnel · claude | cursor | windsurf | copilot
    Force a specific framework instead of auto-detecting. Auto-detection checks for framework-specific files/directories and defaults to Claude Code.
  • beforeHash · string · optionnel
    The `beforeHash` a `brainChange` preview returned. Turns the call into the guarded apply: the change is written only if the current bytes still hash to this value.
  • brainChange · string · optionnel · orientation | config | playbook-index | study-playbook | update-playbook | research-index | kanban-index | kanban-create
    Brain-category-only selector for one stale section (its marker) or the legacy launcher (`launcher`). Without `beforeHash` the call previews that one change read-only; with `beforeHash` it applies it.

  Exemple d'appel

  {"name": "aide_upgrade", "arguments": {"path": "texte", "category": "pointer-stub", "framework": "claude", "beforeHash": "texte", "brainChange": "orientation"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_info≈ 223 tokens

  Boot-time reporter called by the orchestrator at startup. Returns independent top-level fields that the orchestrator must branch on separately: **`outdated` (array of stale artifact keys) — soft notification.** Compares the host's `.aide/versions.json` against the canonical manifest shipped with this npm package. Each element names an artifact key that is behind. An empty array means everything is current. A missing `.aide/versions.json` (old install predating version tracking) silently collapses to `[]`. Staleness is informational — the orchestrator continues with a heads-up to the user. **`behind` (`{ installed, latest }` or null) — soft notification.** Non-null only when the project's `aide` entry launches a globally installed server that is older than the latest published version. Su

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "aide_info", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_brain≈ 510 tokens

  On-demand brain entry-point tool. Call this when you need to reach the brain mid-task — do NOT call it on every /aide boot. Boot-time brain precondition state is already reported by aide_info.brain.status; firing aide_brain at boot duplicates that work unnecessarily. It is also how a brain config is set up, repaired or written for any backend, one decision at a time. Every mode is read-only: no call writes to disk. **Optional `source` parameter** — which read runs. Omitted means `"host"`. - `"host"` — one section of the host's `.aide/config/brain.aide`, described below. - `"template"` — `{ template, purpose }`: one section of the bundled template (or its launcher, with `kind: "launcher"`) as verbatim bytes, and that section's one-line purpose from the published contract. The answer is the

  Paramètres, retour & exemple (3)

  Paramètres

  • kind · string · optionnel · orientation | config | playbook-index | study-playbook | update-playbook | research-index | kanban-index | kanban-create
    Which section: any section marker of the published contract, live or seed, or `launcher` with `source: "template"` only. Omitted means `orientation`. Not accepted with `contract` or `draft`. Seed sections are fetched one per call while seeding.
  • path · string · optionnel
    Project-relative path of a draft brain config. Required with `source: "draft"` and accepted nowhere else; a path outside the project is refused unread.
  • source · string · optionnel · host | template | contract | draft
    Which read runs. Omitted means `host`: one section of the host's `.aide/config/brain.aide`. `template`: one section or the launcher of the bundled template, with its purpose. `contract`: every contract section with its role and purpose. `draft`: a structural check of the draft config at `path`.

  Exemple d'appel

  {"name": "aide_brain", "arguments": {"kind": "orientation", "path": "texte", "source": "host"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_init≈ 516 tokens

  Bootstrap the AIDE development environment into a project. Returns structured JSON for agent consumption — not prose. The tool uses a two-call pattern for progressive disclosure: **First call (no `category` param):** Returns a lightweight summary — every step with `name`, `status` (would-create/would-overwrite/would-skip/exists), `category`, and `filePath`, but NO `content` fields. Also returns `brainHints` (brain root candidates) and detected `framework`. Use this to understand what needs to be done and which categories require user prompts. **Second call (with `category` param):** The tool writes all `would-create` AND approved `would-overwrite` files directly to disk itself and returns a manifest — steps with `filePath`, `status` (`created`, `overwritten`, or `exists`), and `name`, b

  Paramètres, retour & exemple (5)

  Paramètres

  • path · string · optionnel
    Custom project root path (defaults to server working directory)
  • aideMode · string · optionnel · global | local
    Launch mode for the aide MCP entry, chosen by the user (global recommended). Pass with category=mcp. Omitted means local.
  • category · string · optionnel · framework | methodology | commands | agents | skills | mcp | brain | ide
    Write all would-create and approved would-overwrite files for this category to disk and return a manifest (status: created/overwritten/exists; would-skip steps pass through unchanged). Omit on the first call to get a metadata-only summary of all steps.
  • brainMode · string · optionnel · global | local
    Launch mode for the bundled brain template's launcher, chosen by the user in /aide:brain config. Pass with category=brain. Omitted means local.
  • framework · string · optionnel · claude | cursor | windsurf | copilot
    Force a specific framework instead of auto-detecting. Use this when re-calling after the user confirms or overrides detection.

  Exemple d'appel

  {"name": "aide_init", "arguments": {"path": "texte", "aideMode": "global", "category": "framework", "brainMode": "global", "framework": "claude"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• aide_inspect≈ 198 tokens

  Return JSDoc, signature, and kind for a named symbol without opening the full file — Tier 2 progressive disclosure for code. When an agent knows a function name from an import list or orchestrator file, call inspect to learn what the symbol does, what it accepts, and what it returns, based on its contract alone. Searches across TypeScript and JavaScript source files (ts, tsx, js, jsx, mjs, cjs). Use the optional `file` parameter to narrow the search to a single file when the location is already known.

  Paramètres, retour & exemple (2)

  Paramètres

  • file · string · optionnel
    Optional file path to narrow search to a single file
  • name · string · requis
    Symbol name to look up

  Exemple d'appel

  {"name": "aide_inspect", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

Badge pour votre README

Ce serveur a passé le pentest comportemental. Le badge porte son nom et renvoie à cette fiche — la preuve, c'est la fiche (verdict live qu'on contrôle), pas l'image.

[![Vérifié par MCP Hub](https://dokore.fr/badge/io.github.aidemd-mcp--server.svg)](https://dokore.fr/serveur/io.github.aidemd-mcp--server)

<a href="https://dokore.fr/serveur/io.github.aidemd-mcp--server"><img src="https://dokore.fr/badge/io.github.aidemd-mcp--server.svg" alt="Vérifié par MCP Hub" height="20"></a>

Réévalué en continu : si le comportement change, le verdict tombe et le badge disparaît. Un badge qui ne pointe pas vers une fiche dokore.fr ne prouve rien. Comment ça marche

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

@aidemd-mcp/server@0.11.1